Metraipolis › archive › dc_48c78ad86ea0
Stability of Measure-to-Measure Transformers on Sub-Gaussian Data — arXiv:2610.07717
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07717
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:42:35.383Z
- SHA-256 of the archived text
14687b892e38e8b59b1c3294a8319a7b2c9b3822555a2e5061bbeba53a78b190- Stable URL of this page
https://metraipolis.com/documento/dc_48c78ad86ea0
How to cite
Stability of Measure-to-Measure Transformers on Sub-Gaussian Data — arXiv:2610.07717 — arXiv (en), https://arxiv.org/abs/2610.07717 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_48c78ad86ea0 (Metraipolis archive dc_48c78ad86ea0, sha256 14687b892e38e8b59b1c3294a8319a7b2c9b3822555a2e5061bbeba53a78b190)
BibTeX
@misc{dc48c78ad86ea0,
title = {Stability of Measure-to-Measure Transformers on Sub-Gaussian Data — arXiv:2610.07717},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07717},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_48c78ad86ea0; sha256 14687b892e38e8b59b1c3294a8319a7b2c9b3822555a2e5061bbeba53a78b190},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07717. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Transformers have exhibited impressive empirical success across various domains, but their theoretical foundations remain less developed. This work constitutes a mathematical study of the measure-to-measure operators defined by transformers. We show that transformers map sub-Gaussian inputs to sub-Gaussian outputs; this ensures that taking arbitrary-length compositions of the softmax operator is well-defined. We then show that transformers are Hölder continuous with respect to the 1-Wasserstein distance on appropriate spaces of sub-Gaussian inputs. This allows us to establish estimates on the error propagation along a transformer between a sub-Gaussian input and its empirical approximation. We also study a mean-field analog of the cross-attention mechanism, which is an operator from a pair of probability measures to a single probability measure. We show that cross-attention exhibits different Hölder regularity and sample-complexity in its two input arguments. Last, we apply our results to deduce approximation guarantees for measure-to-measure transformers. Together, these results provide a firm stability and finite-sample theory for transformers on sub-Gaussian data. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07717 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:19:24.911Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).